def globs(globs): # setup mock urllib2 module to avoid downloading from mldata.org mock_datasets = { 'mnist-original': { 'data': sp.empty((70000, 784)), 'label': sp.repeat(sp.arange(10, dtype='d'), 7000), }, 'iris': { 'data': sp.empty((150, 4)), }, 'datasets-uci-iris': { 'double0': sp.empty((150, 4)), 'class': sp.empty((150, )), }, } global custom_data_home custom_data_home = tempfile.mkdtemp() makedirs(join(custom_data_home, 'mldata')) globs['custom_data_home'] = custom_data_home global _urllib2_ref _urllib2_ref = datasets.mldata.urllib2 globs['_urllib2_ref'] = _urllib2_ref globs['mock_urllib2'] = mock_urllib2(mock_datasets) return globs
def test_download(): """Test that fetch_mldata is able to download and cache a data set.""" _urllib2_ref = datasets.mldata.urllib2 datasets.mldata.urllib2 = mock_urllib2({'mock': {'label': sp.ones((150,)), 'data': sp.ones((150, 4))}}) try: mock = fetch_mldata('mock', data_home=tmpdir) assert_in(mock, in_=['COL_NAMES', 'DESCR', 'target', 'data']) assert_equal(mock.target.shape, (150,)) assert_equal(mock.data.shape, (150, 4)) assert_raises(datasets.mldata.urllib2.HTTPError, fetch_mldata, 'not_existing_name') finally: datasets.mldata.urllib2 = _urllib2_ref
def globs(globs): # setup mock urllib2 module to avoid downloading from mldata.org mock_datasets = { "mnist-original": {"data": sp.empty((70000, 784)), "label": sp.repeat(sp.arange(10, dtype="d"), 7000)}, "iris": {"data": sp.empty((150, 4))}, "datasets-uci-iris": {"double0": sp.empty((150, 4)), "class": sp.empty((150,))}, } global custom_data_home custom_data_home = tempfile.mkdtemp() makedirs(join(custom_data_home, "mldata")) globs["custom_data_home"] = custom_data_home global _urllib2_ref _urllib2_ref = datasets.mldata.urllib2 globs["_urllib2_ref"] = _urllib2_ref globs["mock_urllib2"] = mock_urllib2(mock_datasets) return globs
def test_fetch_one_column(): _urllib2_ref = datasets.mldata.urllib2 try: dataname = 'onecol' # create fake data set in cache x = sp.arange(6).reshape(2, 3) datasets.mldata.urllib2 = mock_urllib2({dataname: {'x': x}}) dset = fetch_mldata(dataname, data_home=tmpdir) assert_in(dset, in_=['COL_NAMES', 'DESCR', 'data'], out_=['target']) assert_equal(dset.data.shape, (2, 3)) assert_array_equal(dset.data, x) # transposing the data array dset = fetch_mldata(dataname, transpose_data=False, data_home=tmpdir) assert_equal(dset.data.shape, (3, 2)) finally: datasets.mldata.urllib2 = _urllib2_ref
def test_download(): """Test that fetch_mldata is able to download and cache a data set.""" _urllib2_ref = datasets.mldata.urllib2 datasets.mldata.urllib2 = mock_urllib2( {'mock': { 'label': sp.ones((150, )), 'data': sp.ones((150, 4)) }}) try: mock = fetch_mldata('mock', data_home=tmpdir) assert_in(mock, in_=['COL_NAMES', 'DESCR', 'target', 'data']) assert_equal(mock.target.shape, (150, )) assert_equal(mock.data.shape, (150, 4)) assert_raises(datasets.mldata.urllib2.HTTPError, fetch_mldata, 'not_existing_name') finally: datasets.mldata.urllib2 = _urllib2_ref
def test_fetch_multiple_column(): _urllib2_ref = datasets.mldata.urllib2 try: # create fake data set in cache x = sp.arange(6).reshape(2, 3) y = sp.array([1, -1]) z = sp.arange(12).reshape(4, 3) # by default dataname = 'threecol-default' datasets.mldata.urllib2 = mock_urllib2({dataname: ({'label': y, 'data': x, 'z': z}, ['z', 'data', 'label'])}) dset = fetch_mldata(dataname, data_home=tmpdir) assert_in(dset, in_=['COL_NAMES', 'DESCR', 'target', 'data', 'z'], out_=['x', 'y']) assert_array_equal(dset.data, x) assert_array_equal(dset.target, y) assert_array_equal(dset.z, z.T) # by order dataname = 'threecol-order' datasets.mldata.urllib2 = mock_urllib2({dataname: ({'y': y, 'x': x, 'z': z}, ['y', 'x', 'z'])}) dset = fetch_mldata(dataname, data_home=tmpdir) assert_in(dset, in_=['COL_NAMES', 'DESCR', 'target', 'data', 'z'], out_=['x', 'y']) assert_array_equal(dset.data, x) assert_array_equal(dset.target, y) assert_array_equal(dset.z, z.T) # by number dataname = 'threecol-number' datasets.mldata.urllib2 = mock_urllib2({dataname: ({'y': y, 'x': x, 'z': z}, ['z', 'x', 'y'])}) dset = fetch_mldata(dataname, target_name=2, data_name=0, data_home=tmpdir) assert_in(dset, in_=['COL_NAMES', 'DESCR', 'target', 'data', 'x'], out_=['z', 'y']) assert_array_equal(dset.data, z) assert_array_equal(dset.target, y) # by name dset = fetch_mldata(dataname, target_name='y', data_name='z', data_home=tmpdir) assert_in(dset, in_=['COL_NAMES', 'DESCR', 'target', 'data', 'x'], out_=['z', 'y']) assert_array_equal(dset.data, z) assert_array_equal(dset.target, y) finally: datasets.mldata.urllib2 = _urllib2_ref
def test_fetch_multiple_column(): _urllib2_ref = datasets.mldata.urllib2 try: # create fake data set in cache x = sp.arange(6).reshape(2, 3) y = sp.array([1, -1]) z = sp.arange(12).reshape(4, 3) # by default dataname = 'threecol-default' datasets.mldata.urllib2 = mock_urllib2({ dataname: ({ 'label': y, 'data': x, 'z': z }, ['z', 'data', 'label']) }) dset = fetch_mldata(dataname, data_home=tmpdir) assert_in(dset, in_=['COL_NAMES', 'DESCR', 'target', 'data', 'z'], out_=['x', 'y']) assert_array_equal(dset.data, x) assert_array_equal(dset.target, y) assert_array_equal(dset.z, z.T) # by order dataname = 'threecol-order' datasets.mldata.urllib2 = mock_urllib2( {dataname: ({ 'y': y, 'x': x, 'z': z }, ['y', 'x', 'z'])}) dset = fetch_mldata(dataname, data_home=tmpdir) assert_in(dset, in_=['COL_NAMES', 'DESCR', 'target', 'data', 'z'], out_=['x', 'y']) assert_array_equal(dset.data, x) assert_array_equal(dset.target, y) assert_array_equal(dset.z, z.T) # by number dataname = 'threecol-number' datasets.mldata.urllib2 = mock_urllib2( {dataname: ({ 'y': y, 'x': x, 'z': z }, ['z', 'x', 'y'])}) dset = fetch_mldata(dataname, target_name=2, data_name=0, data_home=tmpdir) assert_in(dset, in_=['COL_NAMES', 'DESCR', 'target', 'data', 'x'], out_=['z', 'y']) assert_array_equal(dset.data, z) assert_array_equal(dset.target, y) # by name dset = fetch_mldata(dataname, target_name='y', data_name='z', data_home=tmpdir) assert_in(dset, in_=['COL_NAMES', 'DESCR', 'target', 'data', 'x'], out_=['z', 'y']) assert_array_equal(dset.data, z) assert_array_equal(dset.target, y) finally: datasets.mldata.urllib2 = _urllib2_ref